dice-group / dice-group/gerbil

Problem concerning using Chinese entity linking dataset

Open
#291 2 comments 0 reactions 0 assignees View on GitHub
type:question
Dominant language
Java
Stars
231
Forks
55
PR merge metrics
No merged PRs in 30d

Description

Hi, thank you for sharing and maintaining such a great platform.

Recently I have tried to test the performance of existing EL systems on Chinese EL dataset by using "adding new dataset" in Gerbil. I used a toy Chinese dataset in NIF since it might require some time to transfer the whole dataset into NIF format. Nevertheless, all the existing methods failed to link the mention to the right entity.

I guess it might be attributed to the fact that the EL solutions on the platform do not support Chinese EL task? Or could there be something wrong with the NIF format of the Chinese dataset?

Thank you for your time.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with GERBIL's “adding new dataset” workflow and compare the toy Chinese dataset's NIF format with the input expected by the existing entity-linking methods. Reproduce the failed linking run and determine whether the result is caused by dataset formatting or missing Chinese support; done means the cause is documented and the toy dataset produces correct links or a clearly reported limitation.

Written by the indexing model from the issue text.

Assessment

Tech stack
java
Domain
ai, data
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.